| { |
| "release_date": "2026-10-19", |
| "converted_by": "Jack Spooner", |
| "source": { |
| "repo_id": "Soul-AILab/SoulX-Singer", |
| "revision": "40493ad90286056c7a9095035164434a79daa8c9", |
| "model_card_license": { |
| "language": [ |
| "en", |
| "zh" |
| ], |
| "library_name": "huggingface_hub", |
| "license": "apache-2.0", |
| "pipeline_tag": "text-to-speech", |
| "tags": [ |
| "text-to-audio", |
| "music", |
| "singing-voice-synthesis", |
| "svs", |
| "zero-shot" |
| ] |
| } |
| }, |
| "additional_sources": [ |
| { |
| "repo_id": "Soul-AILab/SoulX-Singer-Preprocess", |
| "revision": "83dc50289d22a81b1e9998f5b9e111aef7c1fdcd", |
| "model_card_license": { |
| "license": "apache-2.0" |
| } |
| }, |
| { |
| "repo_id": "openai/whisper-base", |
| "revision": "e37978b90ca9030d5170a5c07aadb050351a65bb", |
| "model_card_license": { |
| "language": [ |
| "en", |
| "zh", |
| "de", |
| "es", |
| "ru", |
| "ko", |
| "fr", |
| "ja", |
| "pt", |
| "tr", |
| "pl", |
| "ca", |
| "nl", |
| "ar", |
| "sv", |
| "it", |
| "id", |
| "hi", |
| "fi", |
| "vi", |
| "he", |
| "uk", |
| "el", |
| "ms", |
| "cs", |
| "ro", |
| "da", |
| "hu", |
| "ta", |
| "no", |
| "th", |
| "ur", |
| "hr", |
| "bg", |
| "lt", |
| "la", |
| "mi", |
| "ml", |
| "cy", |
| "sk", |
| "te", |
| "fa", |
| "lv", |
| "bn", |
| "sr", |
| "az", |
| "sl", |
| "kn", |
| "et", |
| "mk", |
| "br", |
| "eu", |
| "is", |
| "hy", |
| "ne", |
| "mn", |
| "bs", |
| "kk", |
| "sq", |
| "sw", |
| "gl", |
| "mr", |
| "pa", |
| "si", |
| "km", |
| "sn", |
| "yo", |
| "so", |
| "af", |
| "oc", |
| "ka", |
| "be", |
| "tg", |
| "sd", |
| "gu", |
| "am", |
| "yi", |
| "lo", |
| "uz", |
| "fo", |
| "ht", |
| "ps", |
| "tk", |
| "nn", |
| "mt", |
| "sa", |
| "lb", |
| "my", |
| "bo", |
| "tl", |
| "mg", |
| "as", |
| "tt", |
| "haw", |
| "ln", |
| "ha", |
| "ba", |
| "jw", |
| "su" |
| ], |
| "license": "apache-2.0", |
| "pipeline_tag": "automatic-speech-recognition", |
| "tags": [ |
| "audio", |
| "automatic-speech-recognition", |
| "hf-asr-leaderboard" |
| ], |
| "widget": [ |
| { |
| "example_title": "Librispeech sample 1", |
| "src": "https://cdn-media.huggingface.co/speech_samples/sample1.flac" |
| }, |
| { |
| "example_title": "Librispeech sample 2", |
| "src": "https://cdn-media.huggingface.co/speech_samples/sample2.flac" |
| } |
| ], |
| "model-index": [ |
| { |
| "name": "whisper-base", |
| "results": [ |
| { |
| "task": { |
| "type": "automatic-speech-recognition", |
| "name": "Automatic Speech Recognition" |
| }, |
| "dataset": { |
| "name": "LibriSpeech (clean)", |
| "type": "librispeech_asr", |
| "config": "clean", |
| "split": "test", |
| "args": { |
| "language": "en" |
| } |
| }, |
| "metrics": [ |
| { |
| "type": "wer", |
| "value": 5.008769117619326, |
| "name": "Test WER", |
| "verified": false |
| } |
| ] |
| }, |
| { |
| "task": { |
| "type": "automatic-speech-recognition", |
| "name": "Automatic Speech Recognition" |
| }, |
| "dataset": { |
| "name": "LibriSpeech (other)", |
| "type": "librispeech_asr", |
| "config": "other", |
| "split": "test", |
| "args": { |
| "language": "en" |
| } |
| }, |
| "metrics": [ |
| { |
| "type": "wer", |
| "value": 12.84936273212057, |
| "name": "Test WER", |
| "verified": false |
| } |
| ] |
| }, |
| { |
| "task": { |
| "type": "automatic-speech-recognition", |
| "name": "Automatic Speech Recognition" |
| }, |
| "dataset": { |
| "name": "Common Voice 11.0", |
| "type": "mozilla-foundation/common_voice_11_0", |
| "config": "hi", |
| "split": "test", |
| "args": { |
| "language": "hi" |
| } |
| }, |
| "metrics": [ |
| { |
| "type": "wer", |
| "value": 131, |
| "name": "Test WER", |
| "verified": false |
| } |
| ] |
| } |
| ] |
| } |
| ] |
| } |
| } |
| ], |
| "comfyui": { |
| "repository": "https://github.com/jackspooner/ComfyUI", |
| "compatible_revision": "9d9053c5e7a272f1769886f4d89b6f8a7c79c785", |
| "integration_commit": "26718ef463f8ff72f828f85c527fbaeb1ad686ef", |
| "development_branch": "soulx-singer-native", |
| "implementation": "comfy/ldm/soulx_singer/model.py", |
| "converter": "scripts/convert_soulx_singer.py" |
| }, |
| "changes": "Splits SVS/SVC and their Vocos decoders, extracts Whisper-base encoder-only content weights, folds preprocessing weight normalization and packages RMVPE/karaoke/dereverb. Converts original G2P assets into a data-only pronunciation package; retains CMU dictionary/license. Checkpoint tensors retain FP32 and documented exact round trips.", |
| "verification_limit": "Existing acceptance evidence is linked in README; no new inference or standalone cherry-pick test was performed for this publication.", |
| "original_preprocessing_publishers": [ |
| { |
| "repo_id": "anvuew/dereverb_mel_band_roformer", |
| "revision": "cef05ad2b5b3145ea5c149d3ad5d1f8439b34d06", |
| "declared_license": "gpl-3.0" |
| }, |
| { |
| "repo_id": "becruily/mel-band-roformer-karaoke", |
| "revision": "0c149975cfaa261c7d87baf54330a9da85bcf888", |
| "declared_license": null |
| } |
| ], |
| "distribution_exclusion": "becruily karaoke weights and the workflow requiring them", |
| "license_correction": "Main SoulX SVS/SVC/vocoder weights: Apache-2.0. The optional anvuew dereverb component is GPL-3.0, with original checkpoint, YAML and full corresponding integration/converter source supplied in `source/`. Whisper, G2P and CMU dictionary retain their notices. The becruily karaoke component is withheld because its original publisher declares no redistribution license. No component is relicensed by the mirror\u2019s general Apache metadata." |
| } |
|
|
